A dataset of 51,529 papers and 196,099 reviews across seven OpenReview venues, paired with ReviewArena-Eval, a venue-aware benchmark for evaluating LLM peer reviewers.
@inproceedings{reviewarena2026,title={ReviewArena: A Large-Scale Cross-Conference Dataset and Benchmark for LLM Peer Review},author={P, Samarth and Sathvik, Motamarri Sai and Jain, Vyoman and Golugula, Shiva},booktitle={ICML 2026 Workshop on AI for Science},year={2026},workshop={true},}
A fully decentralized inference framework that self-organizes heterogeneous devices into a peer-to-peer computational ring and automatically shards dense language models according to available compute and memory.
@inproceedings{hypercluster2026,title={HyperCluster: Decentralized Large Language Model Inference over Peer-to-Peer Wireless Networks},author={P, Samarth and Jain, Vyoman and Raghunandan, Sanjiv and Sri, Akepati Ramya and Sharma, Richa},booktitle={IFIP International Conference on Distributed Applications and Interoperable Systems (DAIS)},year={2026},pages={21--35},publisher={Springer},doi={10.1007/978-3-032-27358-1_2},note={Also presented at the AAAI 2026 ML4Wireless workshop (non-archival).}}
An agentic Earth-observation framework that uses TerraMind to retrieve satellite data and dynamically generate geospatial modalities such as NDVI and land-use maps for spatiotemporal reasoning.
@inproceedings{earthinfer2026,title={EarthInfer: Agentic Reasoning with Dynamic Modality Generation for Earth Observation},author={P, Samarth and Rajani, Sakshi},booktitle={WACV 2026 Workshop on Computer Vision for Earth Observation (CV4EO)},year={2026},workshop={true},}
A reproducible comparison of quantum and classical learning models across core tasks, including QNNs, quantum support vector classifiers, QGANs, QCNNs, and quantum autoencoders.
@inproceedings{quantumfrontier2025,title={Benchmarking the Quantum Frontier: Evaluating QML Models on Core Learning Tasks},author={P, Samarth and Shashidhar, Sadhana and Rajani, Sakshi and Masand, Sakshi and Ramasamy, Prema},booktitle={5th International Conference on AI-ML Systems (AIMLSystems)},year={2025},pages={430--435},}
A synthetic document dataset with three interconnected subsets: 3 million richly annotated pages, a 22-language multilingual variant, and an information-retrieval collection of image-query pairs.
@inproceedings{nayana2025,title={Nayana: A Foundation for Document-Centric Vision-Language Models via Multi-Task, Multimodal, and Multilingual Data Synthesis},author={Kolavi, Adithya S and P, Samarth and Jain, Vyoman},booktitle={ICCV 2025 Workshop on Computer Vision for Developing Countries},year={2025},workshop={true},note={Also presented at the CVPR 2025 Vision Language Models for All workshop (non-archival).}}
A layout-aware synthetic-data and parameter-efficient adaptation framework for teaching vision-language models OCR across ten low-resource Indic languages.
@inproceedings{nayanaocr2025,title={Nayana OCR: A Scalable Framework for Document OCR in Low-Resource Languages},author={Kolavi, Adithya S and P, Samarth and Jain, Vyoman},booktitle={Proceedings of the 1st Workshop on Language Models for Underserved Communities, NAACL 2025},year={2025},workshop={true},}
An open-source system that turns papers and natural-language prompts into structured scene descriptions and executable Manim animations using large language models.
@article{manimator2025,title={Manimator: Transforming Research Papers into Visual Explanations},author={P, Samarth and Jain, Vyoman and Golugula, Shiva and Sathvik, Motamarri Sai},journal={arXiv preprint arXiv:2507.14306},year={2025},workshop={true},note={Presented at the ICML 2025 NewInML workshop (non-archival).}}
An adaptation of vision-language models for fine-grained recognition of Bharatanatyam hand gestures, connecting computer vision with Indian classical dance.
@inproceedings{mudravlm2025,title={Mudra-VLM: Adapting Vision-Language Models for Fine-Grained Bharatanatyam Mudra Recognition},author={P, Samarth and Rajani, Sakshi},booktitle={ICCV 2025 Workshop on Computer Vision for Developing Countries},year={2025},workshop={true},note={Non-archival workshop paper.}}
A conversational retrieval interface for accessing community knowledge in colloquial, low-resource Kannada, including multimodal question answering.
@inproceedings{parichaya2024,title={Parichaya: Rural Colloquial Knowledge AI Interface},author={Srivatsa, Sharath and M, Aparna and V, Malavika and P, Samarth and Srinivasa, Srinath},booktitle={Proceedings of the 8th Joint International Conference on Data Science and Management of Data (CODS-COMAD)},year={2024},doi={10.1145/3703323.3704271},}